ASReview: Active learning for Systematic Reviews¶
ASReview is a project to accelerate the process of systematic reviewing. It is written in Python, and uses deep learning to predict which papers should be most likely included in the review. Our software is designed to accelerate the step of screening abstracts and titles with a minimum of papers to be read by a human with no or very few false negatives.
ASReview software consists of a user friendly front-end (ASReview LAB) and a powerful command line interface. The command line interface is to measure the performance of the active learning models on the results of fully labeled systematic reviews.
The source code is freely available at GitHub.
- Quick Tour
- Exploration Mode
- Frequently Asked Questions
The preprint ArXiv:2006.12166 can be used to cite this project.
van de Schoot, Rens, et al. “ASReview: Open Source Software for Efficient and Transparent Active Learning for Systematic Reviews.” ArXiv:2006.12166 [Cs], June 2020. arXiv.org, http://arxiv.org/abs/2006.12166.